Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
render-docx
by ThirstyStudiosRender an XBert working paper as a real .docx file from a structured payload. Use when an XBert plugin (BAS Prep, IAS Prep, FBT Prep, STP Finalisation, Super Check, TPAR, VAT Prep, GST Prep NZ, MTD Prep, Tax Reconciliation, Close Packet, Month-End Pack, FS Pack, Trial Balance Alignment, Balance Sheet Explain, Practice Health Check, Workflow Review, Config Audit, Audit Evidence Pack, Anomaly Review, Policy Review, Client Fee Review, Practice Metrics) has finished its analysis and produced a working-paper payload that needs to become a Word document on disk. Triggers include "working paper", "audit document", "Word document", ".docx", "render the BAS pack", "render the FBT pack", or any consumer-plugin output that names a structured docx deliverable. Do NOT use for raw markdown summaries, chat-only deliverables, Excel schedules (use render-xlsx), PDF-only outputs (use render-pdf), or documents unrelated to XBert plugin payloads.
super-check
by ThirstyStudiosQuarterly Superannuation Guarantee check for Australian clients — verify SG calculated, posted, paid through the clearing house, and lodged by the 28th deadline. Quantifies SGC risk where super is late or missed. Use when the user asks to check super, run an SG review, reconcile the clearing house, check super deadline, or runs the /super-check slash command. Also triggers on: "is super paid", "SG quarterly check", "super clearing house reconciliation", "SGC risk".
close-chase
by ThirstyStudiosClose-period chase methodology — pull all outstanding XBerts for a client, rank by impact and age, draft per-item reminder text with email and Capture-chat tone variants, record the chase and produce a delta on the next run. Use when the user asks to chase outstanding items, run a close-period chase, draft client reminders, get a delta on prior chase, or runs the /close-chase slash command. Also triggers on: "month-end chase", "outstanding XBert chase", "client reminder draft", "close-period sweep".
config-audit
by ThirstyStudiosRun the XBert Config Audit across a Connect tenant — fingerprint per-client XBert rule enablement, segment the book, and surface inconsistencies, gaps and drift with named bulk-normalisation moves. Use when the user asks about XBert configuration consistency, whether rules are set up the same across clients, configuration drift, standardisation, the /config-audit slash command, or 'are we set up consistently'. Distinct from the workflow review skill, which looks at templates and schedules.
end-of-period-dashboard
by ThirstyStudiosRun the XBert End-of-Period Dashboard for a Connect tenant — fuse XBert work, ledger data quality and lodgement obligations into one per-client period-close readiness view. Use when the user asks about month-end, quarter-end, year-end, BAS readiness, payroll close, period-close status, who is ready to close, lodgement deadlines, or runs the /end-of-period-dashboard slash command. Also triggers on 'are we ready for month-end', 'who is at risk for BAS', 'what is blocking close', 'period-close stand-up'.
firm-inbox-triage
by ThirstyStudiosDaily firm-inbox triage — categorise threads, priority-score each, draft tone-matched replies for high-priority threads grounded in XBert client state. Use this skill when the user asks for inbox triage, morning inbox review, daily email sweep, client-aware reply drafting, or runs the /firm-inbox-triage slash command. Also triggers on: 'what's in the inbox this morning', 'triage my email', 'which emails are urgent', 'draft a reply that references the client state', 'inbox overflow', 'pre-client-call inbox check'.
practice-health-check
by ThirstyStudiosRun the XBert Practice Health Check across a Connect tenant — portfolio-wide data-quality and financial-health snapshot with diagnostic and prescriptive recommendations per client. Use when the user asks to assess practice health, sanity-check the book, identify deteriorating clients, find which clients need attention, run a monthly health check, or invokes the /practice-health-check slash command. Also triggers on 'how healthy is my book', 'which clients are slipping', 'where should I focus this month'.
practice-metrics
by ThirstyStudiosProduce the XBert monthly Practice Metrics one-pager — standard partner KPIs, service-line P&L, prior-month variance commentary and RAG-banded client risk view. Use when the user asks for monthly metrics, partner-meeting pack, practice KPIs, lockup days, write-offs, WIP report, service-line P&L, or invokes the /practice-metrics slash command. Also triggers on 'monthly numbers', 'what are our KPIs this month', 'partner pack'.
workflow-review
by ThirstyStudiosRun the XBert Workflow Review against the customer's own Connect tenant — produces a structured audit document covering template consolidation, budget accuracy, workload balance, completion quality, and setup hygiene. Use this skill whenever the user asks to review, audit, or sanity-check their XBert workflow setup, asks how to clean up or rationalise their templates, asks whether their time budgets match reality, asks who is actually doing the work in their team, or runs the /workflow-review slash command. Also triggers on: 'our setup has gotten messy', 'we set this up and never came back to it', 'something is off with our templates', or any request implying a structural audit of workflow configuration.
render-pdf
by ThirstyStudiosRender an XBert working paper as a real .pdf. Use after render-docx has produced a working-paper.docx (preferred path — soffice converts the .docx to PDF preserving styling) or when a consumer plugin (Instalment Variation, Payment Run, Tax Reconciliation, Close Packet, Month-End Pack, FS Pack) emits a payload that needs a standalone authored PDF. Triggers include "PDF working paper", ".pdf", "PDF audit document", "remittance PDF", "render as PDF". Do NOT use for Word working papers (use render-docx) or Excel schedules (use render-xlsx) or chat-only outputs.
render-xlsx
by ThirstyStudiosRender an XBert working-paper schedule as a real .xlsx file from a structured payload. Use when an XBert plugin (Tax Reconciliation, Div 7A Schedule, Trial Balance Alignment, Practice Metrics, FBT Prep, Payment Run, Month-End Pack and similar) has finished its analysis and produced a schedule-shaped payload that needs to become an Excel workbook with formula-live cells. Triggers include "Excel schedule", ".xlsx", "Excel workbook", "tax reconciliation Excel", "Div 7A schedule Excel", "trial balance Excel". Do NOT use for narrative working papers (use render-docx), PDF outputs (use render-pdf), chat-only summaries, or anything that isn't a structured spreadsheet payload.
anomaly-review
by ThirstyStudiosAnomaly-review methodology — verify the Anomaly Review agent is configured with linked XBerts, then present every anomaly XBert that fired across the period as a flat ranked list with per-firing verification and recommended action. No invented pattern labels, no user attribution, no Journal data. Use when the user asks to review anomalies, run an anomaly sweep, debug a recurring anomaly, or runs the /anomaly-review slash command. Also triggers on "anomaly review", "GL anomaly sweep", "fire XBert review", "anomaly evidence pack".
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.